{"id":13754098,"url":"https://github.com/TheDuckAI/arb","last_synced_at":"2025-05-09T22:30:55.205Z","repository":{"id":182641703,"uuid":"668471814","full_name":"TheDuckAI/arb","owner":"TheDuckAI","description":"Advanced Reasoning Benchmark Dataset for LLMs","archived":false,"fork":false,"pushed_at":"2023-11-19T20:40:33.000Z","size":1559,"stargazers_count":45,"open_issues_count":6,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-16T06:31:36.494Z","etag":null,"topics":["benchmark","dataset","llm"],"latest_commit_sha":null,"homepage":"https://advanced-reasoning-benchmark.netlify.app","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TheDuckAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-19T22:27:12.000Z","updated_at":"2024-08-25T03:18:09.000Z","dependencies_parsed_at":"2023-11-19T20:29:00.865Z","dependency_job_id":"b104b103-e60f-4ac6-8da1-f0942c810865","html_url":"https://github.com/TheDuckAI/arb","commit_stats":null,"previous_names":["theduckai/arb-web-interface"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDuckAI%2Farb","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDuckAI%2Farb/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDuckAI%2Farb/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheDuckAI%2Farb/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TheDuckAI","download_url":"https://codeload.github.com/TheDuckAI/arb/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335365,"owners_count":21892658,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["benchmark","dataset","llm"],"created_at":"2024-08-03T09:01:40.176Z","updated_at":"2025-05-09T22:30:54.853Z","avatar_url":"https://github.com/TheDuckAI.png","language":"TypeScript","funding_links":[],"categories":["A01_文本生成_文本对话"],"sub_categories":["大语言对话模型及数据"],"readme":"\u003ch1 align=\"center\"\u003e\n  \u003ca href=\"https://duckai.org\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/TheDuckAI/duck_ai_website/main/public/static/images/twitter-card.png\" alt=\"duckai logo\" width=\"150\"\u003e\u003c/a\u003e\n  \u003cbr/\u003e\n  Advanced Reasoning Benchmark\n  \u003c/br\u003e\n\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://arxiv.org/abs/2307.13692\"\u003e\u003cimg src=\"https://img.shields.io/badge/arXiv-2307.13692-red.svg\" alt=\"arXiv\"\u003e\u003c/a\u003e\n    \u003cimg src=\"https://github.com/TheDuckAI/arb/actions/workflows/lint.yml/badge.svg\" alt=\"Lint Status\"\u003e   \n    \u003cimg src=\"https://img.shields.io/badge/license-MIT-blue?style=flat-square\"\u003e\n\u003c/p\u003e\n\n\u003ch5 align=\"center\"\u003eA \u003ca href=\"https://duckai.org/\" target=\"_blank\"\u003eDuckAI\u003c/a\u003e project in collaboration with the Georgia Institute of Technology, ETH Zürich, Nomos AI, Stanford University Center for Legal Informatics, and the Mila - Quebec AI Institute\u003c/h4\u003e\n\n### Abstract\n\nARB is a novel benchmark dataset composed of advanced reasoning problems designed to evaluate LLMs on text comprehension and expert domain reasoning, presenting a more challenging test than prior benchmarks, featuring questions that test deeper knowledge of mathematics, physics, biology, chemistry, and law.\n\n### API Usage\n\nEndpoint url: https://advanced-reasoning-benchmark.netlify.app/api/\n\u003cbr/\u003e\nThe documentation for the complete REST API of the ARB dataset is [here](https://advanced-reasoning-benchmark.netlify.app/api/).\n\nCopyright © 2023 [DuckAI](https://github.com/TheDuckAI)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheDuckAI%2Farb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTheDuckAI%2Farb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheDuckAI%2Farb/lists"}